# Auditable CT Phenotyping Through Report-derived Radiological Observations

arXiv: https://arxiv.org/abs/2608.25948 · HTML: https://mlsanity.com/paper/2608.25948/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 78 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 4 of 4)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data](https://mlsanity.com/paper/2304.08247/) (2023)
- [F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World](https://mlsanity.com/paper/2603.19223/) (2026)

## Abstract (arXiv)

Medical image foundation models can predict clinical phenotypes from computed tomography (CT), but strong performance leaves open whether they read disease-specific findings or shortcuts that correlate with the diagnosis. We tested this in 221 electronic-health-record (EHR) phenotypes using Auditable CT phenotyping (ACT), built on report-derived radiological observations. We trained ACT on 38,317 patients, mined 376,194 observations and evaluated it in 25,183 held-out patients. ACT exceeded five vision-language baselines on zero-shot annotation, and CT-CLIP across 221 phenotypes from unseen CT pulmonary angiography, both under zero-shot scoring (0.651 versus 0.572) and under linear probing (0.709 versus 0.662). Reading each probe exposes what accuracy conceals: only 97 observations occupy the 221 rank-1 positions, and one phrase describing aortic and coronary calcification ranks first for 20 phenotypes, including osteoporosis, urinary tract infection and major depressive disorder. Restricting the bank to clinician-specified evidence redirects those probes onto phenotype-related observations in 86 phenotypes at no accuracy cost (0.751 versus 0.741). Accurate CT-based EHR phenotyping can therefore rest on observations that are not valid evidence for the coded phenotype and that ACT can identify and intervene on.